The goal scenario asserted a paused revision-2 goal, but the pause is
appended only after cancellation reaches idle — after turn/end. Under
parallel snapshot files the subprocess could dispose before the pause
record persisted, folding the log to an active revision-1 goal.
Add a waitForEventAfterTurnEnd input step (the turn-end/title waiters'
shape, parameterized by event type) and use it in the goal scenario to
hold the subprocess open until the goal-state record lands.
Round-four nits: the acp-snapshot README said 'the suite's hasPwsh probe
follows the executor's own resolution' — hasPwsh is caller-supplied, and the
resolvePwshPath-following behavior belongs to the shipped acp-agent caller;
reword to 'the caller-supplied hasPwsh probe (the shipped acp-agent suite
follows the executor's own resolution...)' on both language sides. And the
tool-bash README loses its only explicit pairing sentence with the dialect
guard reverted, so state the contract plainly: 'The tool contract is
bash-dialect — mount a bash-parsing executor' (both languages, pairing
re-recorded).
The host-variance paragraph documented posixOnly and pinsNativeWindowsStdout
but not the pwshOnly flag and SnapshotSuiteOptions.hasPwsh probe added with
the pwsh-tool-turn scenario; add the parallel sentence on both language
sides and re-record the pairing.
The seam gains ShellDialect ('bash' | 'powershell' - concrete shells, not
families: zsh or fish would be their own values, never 'bash'); bash-local
declares bash (bash-sandbox inherits), pwsh-local declares powershell, and
both tools throw at load when the mounted executor speaks another dialect -
previously tool-pwsh over bash-local handed PowerShell text to bash -c and
the deployment error surfaced as ordinary nonzero exits. Pinned by mismatch
tests on both tools; the parity note records the contract (both languages).
Also from the review round: the tool-bash README's managed-environment
section becomes a summary linking the owning dsh-bash-env contract (the
duplicated prose carried a stale owner in its example import), the
pwshOnly JSDoc drops the stale 'on PATH' phrasing, and the task-tools
contract comment in the two pwsh compositions is indented into its block.
- fromRequest placeholder: the last two braces of a consecutive } run now
terminate the placeholder, so patterns may end with a brace quantifier
(bot warning; the truncated pattern could even silently mis-match since
an unclosed { is literal in JS regexes)
- document that derived JSONL entries pass through the same resolution
- widen ToolRunContext/deferContext seam docs beyond composite-only usage
(source JSDoc, README pair, core-data-structures type-equiv blocks)
- pin direct-human blocked as uninstructed, completing the
goal-round/direct-human x complete/blocked test quadrant
A scripted sidecar cannot know values minted at run time, so terminal
goal updates (which must echo the random goal id) were previously
un-scriptable. Placeholders in scripted entries now resolve against the
request corpus at stream time: last match wins, capture group 1 or the
whole match substitutes, and unmatched/invalid/unterminated patterns
fail loud.
macOS realpaths temp dirs into /private. The normalizer only stripped
the /private prefix for TMPDIR under /var; a TMPDIR under /tmp (any
explicitly relocated temp root) left one side canonicalized and the
comparison failing. Accept both shapes.
The native adapter's route was named deepseek, colliding with pi-ai's
catalog provider of the same name, so the two DeepSeek paths could never
be mounted side by side. The web settings page needs both configurable at
once. Compositions, fixtures, goldens, scaffolding defaults, and docs all
move together (pre-release, no shim); TUI/session-query-spill/
missing-credential goldens re-recorded through their keyless refresh
modes because provider-name length shifts box padding and spill
truncation points.
llm-deepseek gains a Loader+Include composition spec proving external
settings.yaml/.env edits reach the very next request, and a real-API e2e
where only a credentials-local document holds the key. The headless example
pins the first-run missing-credential UX as a keyless stream-json snapshot
(new credentials.cordis.snapshot.yml scenario); runLoaderSmoke learns
expectedExitCode so a designed failure surface can be pinned instead of
masked.
imccyu
Huanqi Cao
Turtle
ZiyaZhang
Dudu-0223
Hypatia May
Yichen Jiang
Tianyi Cui
j-xiang
_Kerman